EP3776101A1

EP3776101A1 - Drink preparation means and method for operating a drink preparation means

Info

Publication number: EP3776101A1
Application number: EP19713374.7A
Authority: EP
Inventors: Philipp Schirrmacher
Original assignee: WMF Group GmbH
Current assignee: WMF GmbH
Priority date: 2018-04-05
Filing date: 2019-03-13
Publication date: 2021-02-17
Also published as: US20210030195A1; CN112136086A; DE102018205153A1; WO2019192812A1

Abstract

The invention relates to a drink preparation means and to a method for operating a drink preparation means. The drink preparation means includes a sensor from a first category, which supplies only one single measured value S1 at a particular point in time, a sensor from a second category, which supplies multiple measured values S2 at a particular point in time, a data memory and a control unit. The control unit is configured to compare the measured values S2 with target values stored in the data memory and, based on this comparison, to trigger or not to trigger at least one event. If the comparison does not lead to the triggering of an event, the control unit detects at least one measured value S1, wherein the measured value S1 is used to allocate the measured values S2 at least to one event and to store these measured values S2 in the data memory as target values for the allocated event.

Description

Beverage maker and method for operating a beverage maker

There are provided a beverage maker and a method for operating a beverage maker. The beverage maker contains a sensor of 1.

Category, which supplies only a single measured value S1 at a certain time, a sensor of a 2nd category, which supplies a plurality of measured values S2 at a specific time, a data memory and a control unit. The control unit is configured to compare the measured values S2 with target values stored in the data memory and based thereon

To trigger at least one event or not trigger. If the comparison does not lead to the triggering of an event, the control unit carries out a detection of at least one measured value S1, the measured value S1 being used to assign the measured values S2 to at least one event and these measured values S2 as target values for the associated event to save to the data store. Machines, such as beverage makers, are primarily designed to receive commands from users and translate them into a result. The commands (eg in the form of entire command chains) are therefore processed by the machine and ended with a result (which can be expected by the user). Complex tasks can no longer be easily solved by the machine in this way, since it is very complex to capture, define and program the complex tasks with their boundary conditions to chain of command. This process takes a lot of time, has a certain risk of error and is associated with high costs.

The term "artificial intelligence" with respect to a computer is understood in common usage to mean that the computer is designed to be capable of solving problems on its own. "Creating an artificial neural network is about software The network evolves in the software by deleting, adding or weighting connections or nodes.

Machine learning is based on algorithms and codes. In machine learning, the machine acquires data, learns from the data, and makes appropriate decisions. The machine learning algorithm can be represented as a flowchart or decision tree. The individual branches of the flowchart or decision tree are weighted by the data collected by the machine.

A supervised learning of a machine depends on a predetermined, to be learned output whose results are known (as of 22.03.2018: https://de.wikipedia.org/wiki/%C3%9Conserved_Learning). The results of the learning process can be compared with the known, correct results, ie "monitored." In general, a learning step looks like this:

1. Create the input;

2. processing the input (propagation);

3. Comparison of the output with the desired value (error);

4. Reduce the error by modifying the weighting (eg with back propagation). In the case of unsupervised learning of a machine, no target values are known in advance. The machine tries to recognize patterns and to interpret them.

In the reverse propagation (English: "backpropagation" = error return), the algorithm runs in the following phases (as of 22.03.2018: https://de.wikipedia.org/wiki/Backpropagation):

1. An input pattern is created and propagated forward through the network;

2. The output of the network is compared with the desired output and the difference of the two values is considered a fault of the network; and

3. The error is now propagated back through the output to the input layer, with the weights of the connections in the network changed depending on their influence on the error. This guarantees an approximation of the desired output when it is applied again.

"Deep learning" is the term used to describe a branch of machine learning, where huge amounts of data are analyzed and patterns are identified and derived.

Artificial intelligence is particularly advantageous when a machine is to perform a certain operation from a complex detection pattern of a sensor (e.g., a collection of multiple measurement points rather than a single measurement).

Sensors can basically be divided into two different categories, namely sensors of the 1st category and sensors of the 2nd category.

Sensors of the first category deliver at a certain time only a single measured value, such as a specific temperature (temperature sensor), a certain pressure (pressure sensor), a certain Geschwin speed (speed sensor), a certain flow rate (flow rate sensor) or a specific electrical Capacity. If this category of sensors measures permanently, individual measured values are obtained as a function of time. The result of the measurement can be represented in an xy-diagram, where x is the time and y the individual Represents measured value. As an example, here is a touch screen of a Getränkeberei age called, on exceeding a certain pressure (pressure sensitive touch screen) or upon detection of a certain capacity (kapa zitiver touch screen) on a particular field of the touch screen a be true event, such as the output of a certain Drinks, causes.

Sensors of the 2nd category deliver not only a single but at least two different measured values at a particular point in time, e.g. the frequency and the amplitude of a longitudinal oscillation (eg acoustic sensor or vibration sensor), the frequency and the amplitude of a transverse oscillation (eg light sensor, IR sensor or radar sensor), a direction and a strength of a magnetic field (magnetic field sensor) or the electrical Conductivity, the pH value and the sugar concentration of a certain liquid (taste sensor). If this category of sensors measures permanently, at least two different measured values are obtained as a function of time. The result of the measurement can be represented on two different measured values in an x-y-z diagram, where x represents the time, y the first measured value and z the second measured value.

Electrical devices (e.g., beverage makers such as coffee makers) prefer to work with sensors of the 1st category because these sensors provide the metrics to be measured without much computational effort. For example, a resistance-based temperature sensor outputs a certain resistance at a certain point in time, and a certain temperature is determined by this particular resistance.

The electrical devices contain software that can dictate how the device reacts when measuring a specific reading at a particular time. For example, an action of the device may be triggered when a certain threshold is exceeded. Generally speaking, the software stores a table in which readings are assigned to a particular device state or action of the device (ie, a particular control command of the device). In this way, the device can be controlled solely via a single measured value of a sensor, for example, a specific action can be performed. In principle, electrical devices can also be controlled with sensors of the 2nd category. Also in this case, tables or patterns can be created, in which an assignment of certain measured values (patterns) acquired by the sensor to one or more actions of the machine is coded. However, the effort required for creating the assignment (s) is significantly higher than for the (simpler) sensors of the 1st category. Reason for the higher effort is that for the command to the device to perform a specific action, at least two readings each have to take a certain, predetermined value ("and" -Switching of y-value and z-value at time x) and so that the complexity of the regulation increases.

It is understood that the increasing demands on electrical equipment (in particular: beverage makers such as coffee machines), i. complex control processes in electrical appliances, in the future only with sensors of the 2nd category can be met.

It is therefore the object of the present invention to provide a beverage maker, which can learn and perform complex control operations in a simple manner and with a minimum effort for a user.

The invention is solved by a beverage maker having the features of claim 1 and a method having the features of claim 8. The dependent claims show advantageous developments.

According to the invention, a beverage maker is provided, comprising a) at least one sensor of a first category, wherein under a sensor the

1st category a sensor is understood, the point at a certain time only a single reading S1 provides;

b) at least one sensor of a second category, wherein under a sensor of

2nd category, a sensor is understood, the points at a certain time point multiple S2 provides;

c) a data store; and

d) a control unit, wherein the control unit is configured to receive the measured values S2 with target values for the measured values S2 which are stored in the data memory and code for at least one specific event compare and, based on this comparison, trigger or not trigger at least one event at the beverage maker;

characterized in that the control unit of the beverage maker is further configured to detect and use at least one measured value S1 to assign at least one event to certain measured values S2 which do not trigger an event after comparison with target values for the measured values S2, and store these measured values S2 as target values for the at least one event on the data memory.

The beverage maker according to the invention is therefore suitable for one or more sensor (s) of the second category contained in the beverage maker with the aid of one or more sensor (s) of the first category contained in the beverage maker for specific, regularly occurring Events, learn. An event in this case is, for example, an output of espresso by the beverage maker confirmed by the user via the at least one sensor of the first category, if the at least one sensor of the second category is an espresso cup at a certain point on the beverage table (eg under a brew group ) detected. The confirmation of the user can be done with the help of a quick and easy push of a button. The storage of the measured values S2 for this event takes place automatically on the data memory.

The advantage of the "learning in" of the beverage maker via at least one sensor of the 1st category is that the effort of learning for the user of the beverage maker is only very slight (for example carrying out a simple push of a button).

If an espresso cup is again placed in the detection area of the at least one sensor of the second category after being taught in, the comparison of the pattern recorded by the sensor of the second category with the pattern stored in the data memory causes the learned event to be performed by the control unit of the beverage maker from the beverage maker automatically (ie without further input of a user) is triggered. The learned, automatically triggered event can be, for example, the display of a "yes / no" query for a particular drink (eg espres so), the display of a timer until a certain drink is dispensed (eg espresso), to display or highlight a particular selection of beverages (eg espresso, ristretto, espresso macchiato) and / or to directly dispense an espresso. If the taught-in event involves the immediate dispensing of an espresso by the beverage maker, the espresso maker automatically dispenses an espresso. In other words, re-confirmation or selection of a user's espresso is no longer necessary. If the taught-in event is the display or highlighting of a particular selection of beverages, the beverage maker automatically displays or highlights the particular selection of beverages. The user can then select a particular drink in this selection. The selection can be made via a sensor of the 1st category, for example, by pressing a button of the beverage maker or touching egg nes field on a touch screen of the beverage maker, or by a sensor of the 2nd category, for example, by carrying out a gesture and / or facial expressions (eg Eye control) in front of a camera of the beverage maker, suc conditions.

The beverage maker according to the invention therefore assigns measured values of sensors of the second category based on a confirmation of a sensor of the first category by a user to certain events, stores this assignment on its data memory and reacts accordingly in the future if an already done (known) Event recurs. This assignment is based on the principle of machine learning.

With increasing frequency of events during the operation of the drinker, the experience of the beverage maker increases. Therefore, the confrontation of the beverage maker with many events increases the likelihood that a certain detection pattern on the sensor of the second category is already known and thus triggers an event even without activating a sensor of the first category. In other words, the link between the patterns detected by the sensor 2 nd category and the associated events increases. Accordingly, the significance of the sensors of the first category is increasingly decreasing and, in the idealized case of a "harvested" beverage maker, no longer plays any role in. The triggered event can also be that, for example, a user interface of the drinks prepared in a certain form, that is, unlike before the event was triggered. This can be on the user interface be a particular beverage selection displayed or highlighted. The choice of a particular beverage in this beverage selection can then be done, for example, by pressing a key (sensor of the 1st category) or by means of a specific gesture (sensor of the 2nd category).

In a preferred embodiment, the invention Ge drink maker includes an operator interface, preferably in the form of a touch screen. The operator interface may be configured to display a triggered event. Further, the operator interface may be configured to show a countdown until the implementation of a triggered event. In addition, the user interface may be configured to display a (specific) beverage selection. Moreover, the operator interface may be configured to display information about measured values S2 of the at least one sensor of a second category, preferably information selected from the group consisting of height of a beverage container, level of a beverage container, level of a bean container of the beverage maker, emptying a mill of the beverage maker and combinations thereof. Furthermore, the operator interface may be configured to display target values for S2 and confirm and / or delete at the request of a user.

The control unit of the beverage maker can be configured to trigger the at least one event coded in the target values for the measured values S2 of the sensor of the second category if the measured values S2 are particularly preferred with a probability of> 50% in each case, preferably> 60% > 70%, very particularly preferably> 80%, in particular> 90%, can assign target values for the measured values S2.

In a preferred embodiment, the control unit of the beverage maker is configured to use at least one measured value S1 if the measured values S2 are particularly preferred with a probability of only <50%, preferably <40%, particularly preferably <30% <20%, in particular <10%, can assign target values for the measured values S2. The at least one sensor of the 1st category can be configured to deliver a one-dimensional measured value S1 at a specific point in time. The one-dimensional measured value can be selected from the group consisting of temperature, pressure, speed, flow velocity, electrical capacitance, direction of movement, distance, time and mass.

The at least one sensor of the 1st category can be selected from the group consisting of temperature sensor, pressure sensor, speed sensor, flow rate sensor, sensor for electrical current and kapaziti ver sensor. Preferably, the at least one sensor of the 1st category is a pressure sensor and / or capacitive sensor. Most preferably, the sensor of the 1st category is a touch screen of the beverage maker.

The at least one sensor of the second category can be configured to deliver multi-dimensional measured values S2 at a specific point in time, preferably at least three-dimensional measured values S2, particularly preferably at least four-dimensional measured values S2. One dimension of the multidimensional measurement value S2 can be selected from the group consisting of frequency of a vibration (eg wavelength of light, ie light color), amplitude of a vibration (eg amplitude of light, ie light intensity), polarization of a vibration (eg polarization of Light), propagation direction of a vibration (eg propagation direction of light), propagation direction of force lines (eg propagation direction of magnetic field lines), strength of force lines (eg strength of magnetic field lines). Another dimension of the multi-dimensional measured value S2 can also be selected from the above-mentioned group, the further dimension then being different from the (first) dimension.

The at least one sensor of the 2nd category can be selected from the group consisting of sensors for the detection of longitudinal vibrations, sensors for detecting transverse vibrations, sensors for detecting magnetic fields, sensors for detecting electric fields, chemical sensors, electrical sensors and combinations here of. The sensor of the second category is preferably selected from the group consisting of sound sensor, vibration sensor, light sensor (eg a camera), IR sensor, radar sensor, magnetic field sensor, conductivity sensor, pH sensor, sensor for detecting a sugar concentration and combinations thereof. The sensor of the second category is preferably a radar sensor, a light sensor (eg a line camera or matrix camera), a sound sensor (eg an acoustic sensor) and combinations thereof.

Radar sensors are particularly preferred sensors of the 2nd category. They have the advantage that they provide very accurate information about the nature of certain beverage containers and thus allow a fine and precise distinction of different beverage containers.

Light sensors, such as line scan cameras or matrix cameras, are also particularly preferred sensors of the 2nd category. They deliver a value y and a value z over a time x in the matrix y / z, where the value y is, for example, a specific light intensity (light brightness) and the value z is, for example, a specific light frequency (light color). With ToF sensors, a spatial distance to the sensor can be recorded as an additional dimension. Light sensors, like radar sensors, are suitable for providing information about the nature of certain beverage containers.

Sound sensors (such as acoustic sensors) are also particularly preferred sensors of the 2nd category. For example, sound sensors are suitable for detecting grinding noise of a grinder (eg for coffee beans) of the beverage preparation age and to prevent emptying of the grinder. For this function, the sound sensor is preferably mounted in the vicinity of a grinder of Ge drink maker. The advantage of using such a sound sensor as a sensor of the 2nd category is that on the recording of this sensor recorded sound pattern a sound pattern just before the emptying of the mill can be used to indicate to the user an early emptying of the grinder. By predicting the early idling of the grinder, a user may be prompted to refill a bean container and thus prevent the bean container from emptying while receiving a beverage (eg, coffee). This causes the provision of a drink (eg coffee) can be carried out without interruption and the beverage maker no downtime occurs. Furthermore, the problem is known that once emptied grinder a certain Advance (ie a certain meal) is required to refill with (ground) beans after refilling the bean container. On the one hand, this prolongs the time until a drink is made available after the triggering of a beverage reference. On the other hand, it comes to Dosierschwankungen Be train to the amount of ground beans that are used for the preparation of the drink and thus to a certain variability in the composition of the related after the idling of the drink beverage. The use of a sound sensor causes the emptying of the grinder can be prevented from the outset. Consequently, the beverage maker can always provide a drink with consistent product composition with no downtime and no delay in feeding.

In a preferred embodiment, the at least one specific event (which can be triggered by the beverage maker) is selected from the group consisting of

i) interaction of the beverage maker with a user, preferably selected from the group consisting of the issue of a request of the beverage maker to the user, display a particular beverage selection, hiding a particular beverage selection and combina tions thereof, the request is particularly preferably selected from refill the group consisting of coffee beans, empty the grounds container, fill the water tank, fill the milk tank, start a maintenance program (eg start a cleaning program, start a descaling program and / or start a washing program) and combinations thereof;

ii) servicing the beverage maker, preferably selected from the group consisting of detecting and / or evaluating errors in expirations of the beverage maker, detecting and / or evaluating errors in components of the beverage maker, determining a service interval of the beverage maker, triggering a service call of the beverage preparing, determining and / or adjusting a setting of the beverage maker;

iii) controlling at least one component of the beverage maker, preferably before dispensing a particular beverage via the beverage maker, moving a beverage dispenser out of the beverage maker, performing a care program of the beverage maker and combinations thereof; and

iv) combinations thereof.

Further, according to the invention, a method for operating a beverage maker is provided, comprising the steps

a) detecting the plurality of measured values S2 of at least one sensor of a second category, wherein a sensor of the second category is understood to mean a sensor which delivers a plurality of measured values S2 at a specific time;

b) comparing the measured values S2 with target values for the measured values S2, which are stored in a data memory of the beverage maker and code for at least one specific event, by a control unit of the beverage maker;

c) triggering or not triggering at least one event at the beverage maker based on that comparison; and

d) detecting at least one measured value S1 of at least one sensor of a first category, if no event is triggered, whereby a sensor of the first category is understood as meaning a sensor which supplies only a single measured value S1 at a specific time;

characterized in that in the case in which, after the comparison with target values for the measured values S2, no event is triggered, the control unit uses at least one measured value S1 of at least one sensor of a first category of the beverage maker to obtain the measured values S2, that after triggering a comparison with target values for the measured values S2, trigger no event, at least one event to be assigned, and these measured values S2 are stored as target values for the at least one event on the data memory.

The beverage maker used in the method according to the invention may contain an operator interface, preferably a touchscreen. The operator interface preferably displays a triggered event. Furthermore, a countdown to the implementation of a triggered event can be displayed via the user interface. In addition, a (specific) beverage selection can be displayed via the operator interface. In addition, information about measuring values S2 of the at least one sensor of a second category are displayed, preferably information selected from the group consisting of height of a beverage container, level of a beverage container, level of a bean container of the beverage maker, emptying a mill of Ge drink maker and combinations thereof. Furthermore, target values for S2 can be displayed via the operator interface and can be confirmed and / or deleted at the request of a user.

In a preferred embodiment of the method, the at least one event coded in the target values for the measured values S2 is triggered if the measured values S2 are most particularly with a probability of> 50%, preferably> 60%, particularly preferably> 70% before giving> 80%, in particular> 90%, to assign target values for the measured values S2.

In the method according to the invention, the at least one measured value S1 can be detected and used, for example, if the measured values S2 have a probability of only <50%, preferably <40%, particularly preferably <30%, very particularly preferably <20%, in particular <10%, can assign target values for the measured values S2.

In a preferred embodiment of the method, the at least one sensor of the 1st category delivers a one-dimensional measured value S1 at a specific point in time. The one-dimensional measured value can be selected from the group consisting of temperature, pressure, speed, Flussge speed, electrical capacitance, direction of movement, distance, time and mass.

The sensor of the 1st category used in the method can have the same properties as the sensor of the first category of the beverage maker described above.

It is further preferred if at least one sensor of the second category is used in the method, which delivers measured values S2 at a certain point in time, preferably at least three-dimensional measured values S2, in particular at least four-dimensional measured values S2. One dimension of the multi-dimensional measured value may be selected from the group consisting of frequency of oscillation (eg wavelength of light, ie light color), amplitude of oscillation (eg amplitude of light, ie light intensity), polarization of oscillation (eg polarization of light), propagation direction a vibration (eg propagation direction of light), propagation direction of force lines (eg propagation direction of magnetic field lines), strength of force lines (eg strength of magnetic field lines). Another dimension of the multidimensional metric may also be selected from the above group.

The sensor of the second category used in the method can have the same properties as the above-described sensor of the second category of the beverage maker.

The method may be characterized in that the at least one specific event is selected from the group consisting of

i) interaction of the beverage maker with a user, preferably selected from the group consisting of the issue of a request of the beverage maker to the user, display a particular beverage selection, hiding a particular beverage selection and combina tions thereof, the request is particularly preferably selected from refill the group consisting of coffee beans, empty the grounds container, fill the water tank, fill the milk tank, start a maintenance program and combinations thereof;

iii) controlling at least one component of the beverage maker, preferably before dispensing a particular beverage via the beverage maker, moving a beverage spout of the beverage maker, executing a beverage program of the beverage maker, and combinations thereof; and iv) combinations thereof.

Based on the following figures and examples, the invention Ge object is to be explained in more detail without wishing to limit this to the illustrated here, specific embodiments.

FIG. 1 shows the functional mechanism of a beverage dispenser according to the invention. If an object to be analyzed is detected by the sensor of the 2nd category 2, the sensor of the 2nd category 2 sends a plurality of measured values 4 (a so-called pattern) to the control unit 6 of the beverage maker. The control unit 6 accesses the data memory 5 and checks whether the detected measured values 4 are already known with a certain probability, i. whether they are stored on the data memory 5 and assigned there a bestimm th event. If this question 7 can be answered in the affirmative, the drinker triggers a certain event 8. If this question is answered in the negative, the beverage maker was switched to a single measured value 3 of the sensor of the 1st category 1. After receiving the measured value 3 of the sensor of the 1st category 1, the measured values 4 recorded by the sensor of the second category 2 are assigned to at least one specific event 8 in the beverage maker. On the data memory 5, no pattern 4 is originally connected to an event 8. A measured value 3 of the sensor of the 1st category 1 is then used to connect a specific event 8 to the measured two measured values 4 of the sensor of the 2nd category 2 and to store this connection on the data memory 5 (= machine learning).

Figure 2 shows the functional mechanism of a beverage according to the invention with a radar sensor 2 for detecting a plurality of measured values 12, 12 ^' of a vessel 10, 10 ^' , which is provided by a user under a drink keausgabeeinheit 11 of the beverage maker.

In FIG. 2A, the vessel is a latte macchiato glass 10 which generates from the radar sensor 2 a frequency spectrum 12 characteristic of this glass 10. In the case of FIG. 2A, this characteristic frequency spectrum 12 is already stored on the data memory 5 of the beverage maker (see V symbol), so that the beverage maker recognizes the latte macchiato glass 10 as such and without further input by the user (eg via an interaction with one 1st category sensor 1) performs an event associated with that glass 10 (eg, dispensing a latte macchiato over the beverage dispenser 11 of the beverage maker or displaying or highlighting a particular beverage selection). If the event is a display or highlighting a certain Beverage selection (eg an enlarged view of certain Ge drinks on a user interface of the beverage maker), so can Be user concrete with a keystroke (actuation of a sensor of the first category) or a gesture, a mimic or an acoustic announcement (Actu tion of a sensor of the 2nd category) a selection and issue of a particular drink be made from the beverage selection).

The same applies to the situation illustrated in FIG. 2B. In FIG. 2B, instead of the latte macchiato glass 10, an espresso cup 10 ^'is placed under the beverage output unit 11 of the beverage maker. Since from the Ra darsensor 2 for the espresso cup 10 ^' detected, characteristic frequency spectrum 12 ^{' is} already stored in the data memory 5 (see V icon), recognizes the beverage maker the espresso cup 10 ^' as such and without further input of the user (eg an interaction with a sensor of the 1st category 1) an event associated with this cup 10 ^' (eg dispensing of an espresso via the beverage dispensing unit 11 of the drinker.

In contrast, FIG. 2C shows a situation in which the pattern 12 detected by the radar sensor 2 for the latte-macchiato glass 10 is not yet stored on the data memory 5 of the beverage maker or has no similarity with patterns stored there (see FIG -Symbol). This causes the beverage maker to acquire a reading from the 1st category 1 sensor (here: a touchscreen 1 on the beverage maker) (here: an impedance change resulting from the touch of a latte-macchiato glass 10 on the touchscreen by a user changes) used to assign the detected pattern 12 to the event "Latte Macchiato output" and to store this assignment on the data memory 5.

FIG. 3 shows an example of several measured values of the sensor of the 2nd category. This sensor of the 2nd category is a two-dimensional len sensor, which in the course of time (x-axis) the intensity (y-axis = 1. Di mension) of electromagnetic radiation of different frequency I, II, III (z-axis = 2nd dimension)) detected.

Example 1 - Beverage maker with electromagnetic sensor for cup detection

The beverage maker is a coffee machine in which a sensor of the 2nd category is installed. This sensor is a radar sensor (for example, a 60Ghz radar sensor from Infineon Technologies AG, Sensitivity: sub-mm range) or an image sensor.

First, a glass or cup is placed under the beverage maker. In the case of a radar sensor, a frequency of the detected radar radiation is measured as the first measured value and an amplitude of the detected radar radiation as the second measured value. In the case of an image sensor, a frequency of the detected light (color of the light) and an amplitude of the detected light (brightness of the light) are detected.

Since no target values are specified on the permanent memory of the beverage maker, there is also no assignment of the measured values (i.e., the pattern) to a specific event.

This beverage maker, as a sensor of the 1st category, has an operator input interface, e.g. a touchpad, up. The operator input interface displays various drinks to the user that can be dispensed by the drinker.

If the user has placed a latte-macchiato glass under the beverage maker, as he wants to have a latte macchiato prepared, the user now selects the output of latte macchiato by pressing the touchpad. The signal of the 1st category sensor (touchpad) is now used to link the signal received via the radar sensor or the image sensor to the output of Latte Macchiato and store this link on the permanent data memory. The next time the same latte-Macchiato glass is placed under the beverage maker, the Issue of Latte Macchiato without confirmation from the touchpad as the beverage maker has assigned the pattern of the particular latte macchiato glass captured by the 2nd category sensor to the Latte Macchiato edition.

Since the shape of latte-macchiato glasses can vary within a series or between different manufacturers, the more often a latte-macchiato glass is placed under the beverage maker, the more the allocation becomes (the increase of the shape information). Even with repeated use of a particular glass, the accuracy increases, since the sensors of the second category can have measurement errors whose significance decreases with each further repetition of the measurement. At some point, an operator input via the touchpad is no longer necessary because the machine clearly assigns the measured values to a latte macchiato glass. On the user interface of the beverage maker (eg display or touch screen), only the beverage can be displayed as a result, which, due to the comparison with the data memory, has matched the last issues with the same pattern S2 and the appropriate key pressure of S1 (here: a bar). macchiato). The user then has the option of selecting the beverage (here: only one latte macchiato shown on the user interface) or, if necessary, canceling it with another command.

Of course, the control unit of the beverage maker may be configured so that the beverage maker offers the user after seating the vessel a beverage selection and / or locks certain drinks. If alternate drinks are not available for a latte macchiato glass, the controller may be configured to automatically start dispensing latte macchiato. This can be done, for example, via a display "Drinking automatically starts in X seconds." To cancel, press Y ", where X stands for seconds and Y stands for a button to be pressed on the beverage maker.

For example, the radar sensor functions as a sensor of the 2nd category so that a part of the radar waves is reflected directly on the surface of the object to be examined (eg a coffee cup) and another part penetrates into the object before the reflection, due to the higher density of the object object Slowed compared to the surrounding air and then exits from the object again. The amount of reflected rays and the transit time differences between the reflecting rays and the emitting rays is characteristic of various objects and materials.

Furthermore, additional information about the glass or the cup can be collected via additional sensors in the beverage maker and assigned to the sensor signals. The following sensors are conceivable:

- Collision detection sensor for determining the height of the vessel;

- Flow sensor for protection against overflow of vessel;

- Pressure sensor to cancel the beverage reference to adapt the Volu menbezugs to the habits of the user.

Example 2 - Beverage maker with acoustic sensor for bean emptying

This beverage maker is a coffee machine and contains an acoustic sensor as a sensor of the 2nd category. For example, the grinder of a coffee maker emits a characteristic sound when emptying it, and this sound can be recorded by the acoustic sensor and linked to the event that the grinder should stop grinding after this "learning process" again the characteristic noise, the mill can be stopped, before it comes to the complete emptying of the mill.

For example, in the prior art, only one current sensor provides information as to whether a mill motor is idling, ie, no longer grinding coffee beans. In this case, the height of the electric current detected by the current sensor decreases. Now, the noise pattern emitted by the mill can be detected and, for example, taught in already 2 to 3 seconds before the current limit value is reached. As a result of this measure, the beverage maker detects a condition shortly before the mill is idling and can switch off the mill in good time (before recognizing the lower current value) .The advantage here is that a product preparation is not interrupted by refilling of beans: in the case of emptying the mill If the grinder and mill spout are empty and after filling with coffee beans, a certain flow (meal) is required to fill the system with beans and ground coffee powder. Only then is ground coffee again conveyed correctly into the brewing chamber. This results in a loss of time and it comes to Dosierschwankungen in relation to the ground coffee.

Also, the noise when refilling beans could be detected and a particular event associated with this process.

LIST OF REFERENCE NUMBERS

1: 1st category sensor (e.g., touch display);

2: 2nd category sensor (e.g., radar sensor);

3: single measured value S1 of the sensor of the 1st category (for example, a discrete one

Pressure value of a pressure sensor);

4: a plurality of measured values S2 of the sensor of the 2nd category (for example spatially resolved discrete frequencies and discrete intensities of an electromagnetic radiation);

5: data memory;

6: control unit;

7: determination of whether measured values 4 are present in data memory 5;

8: event triggered by the beverage maker;

9: Assignment of measured values 4 to at least one event;

10: latte macchiato glass;

10 ': espresso cup;

11: drink dispensing unit of the beverage maker;

12: frequency spectrum of a latte macchiato glass 10;

12 ': frequency spectrum of an espresso cup 10';

I: 1st frequency of electromagnetic radiation;

II: 1. Frequency of electromagnetic radiation;

III: 3rd frequency of electromagnetic radiation;

Claims

claims

1. Beverage preparator, containing

a) at least one sensor of the first category, whereby a sensor of the first category is understood as meaning a sensor which supplies only a single measured value S1 at a specific time; b) at least one sensor of a second category, wherein a sensor of the second category is understood as meaning a sensor which delivers a plurality of measured values S2 at a specific time;

c) a data store;

d) a control unit, wherein the control unit is configured to compare the measured values S2 with target values for the measured values S2 which are stored in the data memory and code for at least one specific event and based on this comparison at the beverage maker at least one event to trigger or not to trigger;

characterized in that the control unit of the beverage maker is further configured to detect and use at least one measured value S1 to associate at least one event with certain measured values S2 which do not cause an event after comparison with target values for the measured values S2 Store measured values S2 as target values for the at least one event on the data memory.

2. beverage maker according to the preceding claim, characterized in that the beverage maker includes an operator interface, preferably a touch screen, wherein the operator interface is preferably configured to

i) indicate a triggered event; and or ii) indicate a countdown to the implementation of a triggered event; and or

iii) indicate a beverage selection;

iv) display information about measured values S2 of the at least one sensor of a second category, preferably information selected from the group comprising height of a beverage container, level of a beverage container, level of a bean container of the beverage maker, emptying a mill of the drinker and combinations thereof ; and / or v) display target values for S2 and confirm and / or delete at the request of a user.

3. beverage maker according to one of the preceding claims, characterized in that the control unit is configured to trigger the encoded in the target values for the measured values S2 at least one event if the measured values S2 with a probability probability of> 50%, preferably> 60%, particularly preferably> 70%, very particularly preferably> 80%, in particular> 90%, can assign target values for the measured values S2.

4. beverage maker according to one of the preceding claims, characterized in that the control unit is configured to use at least one measured value S1, if the Messwer te S2 with a probability of only <50%, preferably <40%, particularly preferably <30%, very particularly preferably <20%, in particular <10%, can assign target values for the measured values S2.

5. Beverage maker according to one of the preceding claims, characterized in that the at least one sensor of the first category is configured to supply at a certain point in time only a one-dimensional measured value S1.

6. Getränkebereiter according to one of the preceding claims, characterized in that the at least one sensor of the 2nd category is configured to at a certain time mehrdi- to provide dimensional measured values S2, preferably at least three-dimensional measured values S2, particularly preferably at least four-dimensional measured values S2.

7. beverage maker according to one of the preceding claims, characterized in that the at least one specific event is selected from the group consisting of interaction of the beverage kebereiters with a user, maintenance of Getränkeberei ester, controlling at least one component of the beverage maker and combinations thereof.

8. A method of operating a beverage maker comprising the steps

a) detecting the plurality of measured values S2 of at least one Sen sor a second category, wherein a sensor of the second category, a sensor is understood, which provides a plurality of measured values S2 at a given time;

c) triggering or not triggering at least one event at the beverage maker based on that comparison; and d) detecting at least one measured value S1 of at least one sensor of a first category if no event is triggered, whereby a sensor of the first category is understood as meaning a sensor which supplies only a single measured value S1 at a specific time;

characterized in that in the case in which, after the comparison with target values for the measured values S2, no event is triggered, the control unit uses at least one measured value S1 of at least one sensor of a first category of the beverage maker to obtain the measured values S2, after a comparison with target values for the measured values S2, trigger no event, at least one event can be assigned and these measured values S2 are stored as target values for the at least one event on the data memory.

9. The method according to claim 8, characterized in that the beverage kebereiter an operator interface, preferably a touch screen, ent holds, preferred over the operator interface

i) a triggered event is displayed; and or

ii) a countdown is displayed until the implementation of a triggered event; and or

iii) a beverage selection is displayed;

iv) information about measured values S2 of the at least one sensor of a second category are displayed, preferably information selected from the group consisting of height of a beverage container, level of a beverage container, level of a Boh nenbehälters the beverage maker, emptying a mill of the beverage maker and combinations thereof; and / or v) target values for S2 are displayed and confirmed and / or deleted at the request of a user.

10. The method according to claim 8 or 9, characterized in that the coded in the target values for the measured values S2 at least one event is triggered when the measured values S2 with a probability of each> 50%, preferably> 60%, especially preferably> 70%, very particularly preferably> 80%, in particular> 90%, can assign target values for the measured values S2.

11. The method according to any one of claims 8 to 10, characterized in that at least one measured value S1 is detected and used when the measured values S2 with a probability of only <50%, preferably <40%, particularly preferably <30% , very particularly preferably <20%, in particular <10%, can be assigned target values for the measured values S2.

12. The method according to any one of claims 8 to 11, characterized in that the at least one sensor of the 1st category at a certain point in time delivers a one-dimensional measured value S1.

13. The method according to any one of claims 8 to 12, characterized in that the at least one sensor of the 2nd category at a certain point in time provides multidimensional measured values S2, preferably before at least three-dimensional measured values S2, in particular at least four-dimensional measured values S2.

14. The method according to any one of claims 8 to 13, characterized in that the at least one specific event is selected from the group consisting of interaction of the beverage maker with egg nem user, maintenance of the beverage maker, control min least one component of the beverage maker and combinations thereof ,